检索结果-内蒙古大学图书馆

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Delnevo, Giovanni Olaiya, Kelvin Salomoni, Paola University of Bologna Dept. of Computer Science and Engineering Bologna Italy

ISBN: (纸本)9798331508050

This paper explores the evolving concept of digital sustainability, emphasizing its growing importance as digital technologies become essential to addressing global sustainability challenges. Through a thematic literature review focused on computer science, we analyze papers from Scopus-indexed journals to identify key themes in the discourse on digital sustainability. Additionally, we map the identified topics to the traditional three-pillar model of sustainable development, noting areas of alignment and divergence. The study offers insights into how digital sustainability is framed within the computer science literature and its implications for future research. © 2025 IEEE.

关键词： Green development

来源：评论

学校读者我要写书评

暂无评论

Deep Analysis of Machine Learning Techniques for the Effective Retrieval of Images Based on Content 2

Deep Analysis of Machine Learning Techniques for the Effecti...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Jain, Ashish Varshney, Sudeep Set Sharda University Dept. of Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

Our research aims to investigate how machine learning techniques can be applied for efficient image retrieval based on content. It is a very difficult process to obtain accurate images from vast digital image collections. CBIR has been particularly interested in this area. It has been shown that content- or feature-based approaches are more effective than text-based query techniques. Research has shown that the performance of these methods varies depending on the type and size of the data set analyzed, with some algorithms performing well for specific small data sets and others for larger data sets. This article provides a comprehensive and systematic review of effective methods for obtaining the image. The paper's objective is to examine different ML classifiers that are applied via the researchers and compare their results based on accuracy and performance. These algorithms include SVM, KNN, random forest, BoVW, Naive Bayes, and LDA. This review paper can assist researchers in selecting the best classifier for their research, as well as in improving existing classifiers by combining them with other algorithms. © 2024 IEEE.

关键词： CBIR classifier feature extraction Random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

Inside-Outside Algorithm for Probabilistic Product-Free Lambek Categorial Grammar 31

Inside-Outside Algorithm for Probabilistic Product-Free Lamb...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhao, Jinman Penn, Gerald Dept. of Computer Science University of Toronto Canada

ISBN: (纸本)9798891761964

The inside-outside algorithm is widely utilized in statistical models related to context-free grammars. It plays a key role in the EM estimation of probabilistic context-free grammars. In this work, we introduce an inside-outside algorithm for Probabilistic Lambek Categorical Grammar (PLCG). © 2025 Association for Computational Linguistics.

关键词： Context free grammars

来源：评论

学校读者我要写书评

暂无评论

Analysis of Shaft Voltage Characteristics According to Rotor Overhang of Wound-Field Rotor Synchronous Motor for Electric Vehicle

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第10期73卷 1648-1653页

作者： Lee, Jin-Hwan Yoon, Han-Joon Kim, Yong-Jae Jung, Sang-Yong Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Dept. of Electrical Engineering Chonnam National University Korea Republic of Dept. of Electrical Engineering Chosun University Korea Republic of

This study analyzes the characteristics of shaft voltage due to rotor overhang in a wound-field rotor synchronous motor(WRSM) for electric vehicle. Recently, WRSM have gained significant attention as alternatives to permanent magnet motors. However, they exhibit disadvantages in torque density compared to permanent magnet motors, since they do not utilize permanent magnets. To solve this drawback, rotor overhang is commonly applied, but this can adversely affect voltage insulation due to end leakage flux. To verify this, models without and with rotor overhang are separately modeled to analyze shaft voltage characteristics. The results confirm the impact of rotor overhang on shaft voltage in the design of WRSM. Copyright © The Korean Institute of Electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Deep Neural Network for Early Detection and Classification of Chicken Diseases 5

A Novel Hybrid Deep Neural Network for Early Detection and C...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Uddin, Md Shihab Islam, Md Fakrul Rahman, Sharukh Foysal, Nasir Uddin Islam, Muhammad Nazrul Razzaque, Md. Abdur Al Faisal, Faiz Green University of Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Military Institute of Science and Technology Dept. of Computer Science and Engineering Dhaka1216 Bangladesh University of Dhaka Dept. of Computer Science and Engineering Dhaka1000 Bangladesh

ISBN: (纸本)9798350394290

Detection and classification of chicken diseases has been a longstanding concern for farmers. Relying solely on expert opinions could be a costly option. Moreover, there are certain chicken diseases that spread quickly, and necessary procedures are immediately needed to carryon. On the other hand, the lack of research activity or low availability of data on this topic leads to many misunderstandings and challenges so as to correctly detect a certain type of chicken disease. The existing techniques show low accuracy on disease classification, which leads to a complex engineering problem and critical analysis is required for sustainable development. In this paper, we develop a novel hybrid deep neural network, namely ChickenNet21, which combines a Convolutional Neural Network (CNN) and a fine-tuned Visual Geometry Group (VGG) model to address this challenge. Using a large dataset of 6,812 farm-labeled fecal images, we assess the effectiveness of ChickenNet21 and it achieves 98.83% accuracy in identifying chicken diseases. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting Retinal Damage From OCT Images 15

Detecting Retinal Damage From OCT Images

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vineetha, Kundrapu Ali, Md Jaffer Prathima, Narisetty Singh, Tripty Duraisamy, Prakash Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India University of Wisconsin-Green Bay Dept. of Computer Science and Engineering Wisconsin United States

ISBN: (纸本)9798350370249

Optical coherence tomography (OCT) is a crucial imaging modality in ophthalmology, offering detailed retinal images essential for diagnosing various retinal disorders. In this study, we investigate the application of convolutional neural networks (CNNs) and transfer learning to classify retinal OCT images. We compare a custom CNN model with two pretrained models, MobileNet and VGG16, to explore their effectiveness in categorizing retinal diseases. Our study focuses on improving classification accuracy through image enhancement techniques, training methodologies, and model evaluation using confusion matrices. The results highlight the VGG16-based CNN model as the most effective, demonstrating its potential for accurate classification of retinal disorders based on OCT images. Furthermore, we delve into strategies to further enhance the performance of these models, such as data augmentation, finetuning, and hyperparameter tuning. We discuss the importance of these techniques in optimizing model performance and reducing overfitting. Additionally, we emphasize the significance of evaluating models using confusion matrices to gain insights into their performance across different classes. Overall, our findings suggest that CNNs, particularly the VGG16based model, hold promise for improving the automated diagnosis of retinal diseases using OCT imaging, which could lead to better patient outcomes in ophthalmology. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intensify Stroke Prediction Model Associated with Hypertensive State 3

Intensify Stroke Prediction Model Associated with Hypertensi...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Islam, Md. Rabiul Rahman, Mst. Sahela Paul, Radha Rani Hosen, Md. Fahad Khairunnahar, Mst. Nayeem, Md. Julker Pundra University of Science & Technology Dept. of Computer Science & Engineering Bogura5800 Bangladesh

ISBN: (纸本)9798350388282

Hypertension and stroke are significant worldwide health issues with high prevalence and complex health hazards. Hypertensive state implications include death or major complications such as myocardial infarction. This study leverages data from the Internet to foresee the prognosis for individuals with hypertensive strokes. There are two main components to the clinical outcome prediction in this study. The value of various variables is ranked by our model through the use of cross-validation techniques, recursive feature disposal, and classification algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). Our empirical cross-validation results demonstrate the remarkable predictive reliability of both LR and RF once repetitive features are removed, even with a smaller set of features and classifiers. Particularly in terms of accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), logistic regression performs better than the other two classifiers. Likewise, we conducted independent prediction analyses for hypertension, hypertensive stroke, and stroke. The highest result of 96.15% is obtained using logistic regression for stroke prediction. The random forest classifier has an accuracy of 91.25% for hypertension, and combining stroke with a hypertension support vector classifier gives 91.72% accuracy. This demonstrates how well it might provide patients with hypertensive strokes with precise and trustworthy projections. Finally, our study illuminates the potentially useful prediction powers of particular algorithms in determining the prognosis of patients with hypertensive strokes. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Virtual Video Game as a Clinical Tool for Psychological Assessment and Analysis

Virtual Video Game as a Clinical Tool for Psychological Asse...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Gope, Aditya Kumar Pohane, Karthik Jakkanwar, Shivam Ramasamy, Gobi Dept. of Computer Science Bangalore India

ISBN: (纸本)9798350309140

This paper proposes a very novel and dynamic approach to psychological assessment by utilising virtual video games as a psychometric tool. Traditional methods, such as interviews and surveys, often yield conscious responses, leading to potential inaccuracies. Leveraging the interactive and immersive nature of video games, our research aims to enhance the accuracy and engagement of data collection. We introduce a dynamic scale to quantify player responses, providing a structured framework for systematic assessment. Collected data can be analysed using statistical models or customised by experts to evaluate psychological indicators precisely. This research explores the benefits of virtual video games in improving the accuracy, engagement, and flexibility of psychological assessments, contributing to more effective solutions in clinical psychology. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Semantic Masking in a Needle-in-a-haystack Test for Evaluating Large Language Model Long-Text Capabilities 1

Semantic Masking in a Needle-in-a-haystack Test for Evaluati...

引用

1st Workshop on Writing Aids at the Crossroads of AI, Cognitive science and NLP, WRAICOGS 2025

作者： Shi, Ken Penn, Gerald Dept. of Computer Science University of Toronto Canada

ISBN: (纸本)9798891762213

In this paper, we introduce the concept of Semantic Masking, where semantically coherent surrounding text (the haystack) interferes with the retrieval and comprehension of specific information (the needle) embedded within it. We propose the Needle-in-a-Haystack-QA Test, an evaluation pipeline that assesses LLMs’ long-text capabilities through question answering, explicitly accounting for the Semantic Masking effect. We conduct experiments to demonstrate that Semantic Masking significantly impacts LLM performance more than text length does. By accounting for Semantic Masking, we provide a more accurate assessment of LLMs’ true proficiency in utilizing extended contexts, paving the way for future research to develop models that are not only capable of handling longer inputs but are also adept.at navigating complex semantic landscapes. © WRAICOGS 2025 - Writing Aids at the Crossroads of AI, Cognitive science and NLP, Proceedings of the 1st Workshop.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

Maskify: Precision Detection and Fit Assessment for Mask Compliance 6

Maskify: Precision Detection and Fit Assessment for Mask Com...

引用

6th IEEE International Conference on Image Processing, Applications and Systems, IPAS 2025

作者： Pathak, Prakrit Garg, Ayush Kumar Chaurasia, Priyesh IIIT-Delhi Dept. of Computer Science India

ISBN: (纸本)9798331506520

We introduce Maskify, an innovative tool designed to automatically detect and evaluate the use of face masks. Amid the challenges of the COVID-19 pandemic, wearing masks has emerged as a crucial strategy to limit the virus's spread, especially in environments where mask mandates are enforced. Reliable systems for monitoring mask usage are therefore vital for public *** solution leverages deep learning to not only determine if a person is wearing a mask but also to assess how well the mask fits using a specialized metric called the "wearable score."This score quantifies the extent to which the mask properly covers essential areas of the face. Developing Maskify involved creating a diverse dataset that includes images of both masked and unmasked *** process begins with advanced pre-trained models that accurately identify faces in images. Once a face is detected, key landmarks on the lower face are extracted to assist in classifying the mask. We utilize ResNet-based architectures, known for their robust image classification performance, to enhance the detection accuracy. The wearable score is then computed by segmenting the mask region and calculating the percentage of the face that is effectively *** summary, Maskify offers a robust approach for monitoring mask compliance and ensuring proper fit, thereby supporting ongoing public health efforts to mitigate the spread of COVID-19. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：